System control method and device for textile system

Abstract

The embodiment of the invention provides a system control method and device for a textile system, and relates to the technical field of textile system control technologies. The method comprises the steps that sensing data of the textile system are obtained, the sensing data are obtained by conducting sensing detection on the textile system through a plurality of preset sensors, the sensing data comprise at least any one of equipment state data, working environment data and network transmission data, the sensing data are preprocessed, and the preprocessed sensing data are sent to the textile system; the preprocessing comprises the steps of performing data filtering on the sensing data, acquiring result data of a finished product as second data, determining a first control strategy according to the second data, generating a first control instruction according to the first control strategy, and sending the first control instruction to the textile system, and the textile system is indicated to execute the target operation based on the first control instruction, so that the system control precision and efficiency are effectively improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of textile system control, and in particular, to a system control method and device for a textile system. Background Art

[0002] The textile industry is a long-standing and growing field that relies on efficient production processes and precise quality control to remain competitive. With the advancement of technology, automation and intelligent control systems have been widely used in textile production to improve production efficiency, reduce labor costs, ensure product quality and meet the growing market demand.

[0003] At present, the control methods of textile systems mainly include traditional PLC (Programmable Logic Controller)-based automatic control systems, computer-based monitoring systems, and some primary machine learning algorithms. These methods have improved production efficiency and product quality to a certain extent, but there are still some limitations, and the existing textile systems cannot achieve good production efficiency.

[0004] There is currently no better solution to the above problems. Summary of the invention

[0005] The embodiments of the present invention provide a system control method and device for a textile system, so as to at least solve the problems of low control accuracy and production efficiency of the textile system in the related art.

[0006] According to one embodiment of the present invention, there is provided a system control method for a textile system, comprising:

[0007] Acquiring sensor data of a textile system, wherein the sensor data is obtained by performing sensor detection on the textile system through a plurality of preset sensors, wherein the sensor data includes at least any one of equipment status data, working environment data, and network transmission data;

[0008] Preprocessing the sensor data to obtain first data, wherein the preprocessing includes filtering the sensor data;

[0009] Acquire result data of the finished product as second data, and determine the first control strategy according to the second data;

[0010] A first control instruction is generated according to the first control strategy, and the first control instruction is sent to the textile system to instruct the textile system to perform a target operation based on the first control instruction.

[0011] In an exemplary embodiment, obtaining result data of the finished product as second data, and determining the first control strategy according to the second data include:

[0012] The result data of the finished product is obtained as the second data, and whether the first data is abnormal is determined according to the second data, and the first control strategy is determined according to the abnormality of the first data.

[0013] In an exemplary embodiment, obtaining the result data of the finished product as the second data, determining whether the first data is abnormal according to the second data, and determining the first control strategy according to the abnormality of the first data include:

[0014] When the second data is lower than a preset standard yield rate threshold, it is determined that the first data is abnormal.

[0015] In an exemplary embodiment, obtaining the result data of the finished product as the second data, determining whether the first data is abnormal according to the second data, and determining the first control strategy according to the abnormality of the first data include:

[0016] When it is determined that the first data is abnormal, determine whether a certain item of the first data seriously deviates from the normal value. If all items of the first data do not seriously deviate from the normal value, adjust all items of the first data one by one. When adjusting to a certain item of data, if the second data is higher than the preset standard yield threshold, mark the detection point of the data as an abnormal detection point.

[0017] In an exemplary embodiment, the obtaining of result data of the finished product as the second data, and determining the first control strategy according to the second data, further comprises:

[0018] A high value in the second data is obtained, and the first data in the high value of the second data is used as standard data, an average of all items of data in the standard data is taken as a standard adjustment value, and the standard adjustment value is applied in the production line.

[0019] According to another embodiment of the present invention, there is provided a system control device for a textile system, comprising:

[0020] A data acquisition module, used for acquiring sensor data of the textile system, wherein the sensor data is obtained by sensing and detecting the textile system through a plurality of preset sensors, wherein the sensor data includes at least any one of equipment status data, working environment data and network transmission data;

[0021] A preprocessing module, used for preprocessing the sensor data to obtain first data, wherein the preprocessing includes sequentially performing data filtering and normalization processing on the sensor data;

[0022] A strategy generation module, used for obtaining result data of the finished product as second data, and determining a first control strategy according to the second data;

[0023] An instruction generation module is used to generate a first control instruction according to the first control strategy, and send the first control instruction to the textile system to instruct the textile system to perform a target operation based on the first control instruction.

[0024] In an exemplary embodiment, it further includes:

[0025] An abnormal point determination module is used to determine whether a certain item of the first data seriously deviates from the normal value when it is determined that the first data is abnormal. If all items of the first data do not seriously deviate from the normal value, all items of the first data are adjusted one by one. When adjusting to a certain item of data, if the second data is higher than the preset standard yield threshold, the detection point of the data is marked as an abnormal detection point.

[0026] In an exemplary embodiment, the legitimacy detection module includes:

[0027] Data adjustment module: obtains the high value in the second data, and uses the first data in the high value of the second data as the standard data, takes the average of all items of data in the standard data as the standard adjustment value, and applies the standard adjustment value in the production line.

[0028] According to yet another embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any one of the above method embodiments when run.

[0029] According to yet another embodiment of the present invention, there is provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0030] Through the present invention, since the system status automatically generates a corresponding control strategy according to different yield results, it is possible to find which specific link has a problem when the yield is low, and to determine whether the detection device has a problem even if there is no problem with the data. At the same time, when the yield is the highest, the data of each link when the yield is the highest can be applied, so that each device of the system can be continuously and rationally controlled during the textile process, thereby effectively improving the system control accuracy and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1is a flow chart of a system control method for a textile system according to an embodiment of the present invention;

[0032] Figure 2 It is a schematic diagram of the principle of a specific embodiment of the present invention. Figure 1 ;

[0033] Figure 3 It is a schematic diagram of the principle of a specific embodiment of the present invention. Figure 2 ;

[0034] Figure 4 4 is a structural block diagram of a system control device for a textile system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings and in combination with the embodiments.

[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0037] In this embodiment, a system control method for a textile system is provided. Figure 1 is a flow chart of a system control method for a textile system according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0038] Step S100, acquiring sensor data of the textile system, wherein the sensor data is obtained by performing sensor detection on the textile system through a plurality of preset sensors, wherein the sensor data includes at least any one of equipment status data, working environment data and network transmission data;

[0039] In this embodiment, data of each device and module in the textile system is obtained to facilitate determination of corresponding scheduling or working strategies based on the data, so as to achieve control of the textile system and improve production efficiency.

[0040] Among them, sensors for data sensing include (but are not limited to) temperature and humidity sensors, vibration sensors, pressure sensors, noise sensors, gateways for transmitting network data, and corresponding data sensors for collecting environmental and equipment data; correspondingly, equipment status data include temperature, pressure, production speed, downtime and other data of related equipment in the textile system, environmental sensors include temperature and humidity, light intensity, noise level and other data of the production environment, network transmission data includes data transmission speed, node status and other data of the communication network of the textile system; of course, in addition to the above data, data can also be collected through automatic counting and automatic quality inspection equipment of warehouse management and quality inspection department to obtain production yield / defective rate, energy consumption and other data.

[0041] Step S200, preprocessing the sensor data to obtain first data, wherein the preprocessing includes filtering the sensor data;

[0042] In this embodiment, the data is filtered to reduce the interference of unreasonable data on subsequent data analysis, wherein data interference refers to a single deviation in a single item of data, and this single deviation is not included in this application, thereby facilitating subsequent data analysis.

[0043] Step S300, taking the result data of the finished product as the second data, and determining the first control strategy according to the second data;

[0044] In this embodiment, the first control strategy includes (but is not limited to) the path, time, quantity, speed, etc. of scheduling and regulating different equipment in the textile system, and includes the adjustment of the temperature and humidity of the environment.

[0045] Specifically, the result data of the finished product is obtained as the second data, and whether the first data is abnormal is determined according to the second data, and the first control strategy is determined according to the abnormal situation of the first data.

[0046] Among them, the result data of the finished product includes the yield rate and the quantity of finished products. In this embodiment, when the difference range of the finished product quantity is small, only the yield rate is considered, and the first data includes the production path, production temperature, production humidity, production speed, start-up time, working conditions of components, etc. of the equipment.

[0047] Furthermore, when the second data is lower than the preset standard yield threshold, the first data is determined to be abnormal, and when the yield is lower than the preset yield threshold, it is determined to be a production abnormality. If it is determined to be a production abnormality, two situations will occur. One is that the production data is not abnormal but the yield is abnormal, and the other is that the production data is abnormal and the yield is abnormal. Regardless of which of the above, in this embodiment, it is determined that the first data is abnormal.

[0048] In this embodiment, when it is determined that the first data is abnormal, it is determined whether a certain item of the first data seriously deviates from the normal value. If all items of the first data do not seriously deviate from the normal value, all items of the first data are adjusted one by one. When adjusting to a certain item of data, if the second data is higher than the preset standard yield threshold, the detection point of the data is marked as an abnormal detection point.

[0049] Specifically, after data processing, a certain item of data in the first data still seriously deviates from the normal value, which means that the detection device corresponding to the data or the corresponding production equipment that affects the data has an abnormality. At this time, it means that the detection device corresponding to the data or the corresponding production equipment that affects the data needs to be repaired and adjusted. At this time, the corresponding maintenance personnel are notified to operate until the repair is completed. When all items of data in the first data do not seriously deviate from the normal value, it means that there is a problem with the detection component in a certain device. At this time, it is necessary to adjust all items of data in the first data one by one, that is, adjust the production equipment that affects each item of data in the first data, and adjust them one by one for investigation. When the yield rate approaches the positive output value when adjusting to a certain data, it is determined that there is a problem with the detection component corresponding to the data, and the component is replaced. However, this method is mostly suitable for production lines with a small amount of data in the first data and a small production volume.

[0050] It also includes obtaining a high value in the second data, and using the first data in the high value that generates the second data as standard data, taking the average of all item data in the standard data as a standard adjustment value, and applying the standard adjustment value in the production line.

[0051] Among them, various data in each time period are recorded. When the yield rate in a certain time period is high, that is, when a high value appears in the second data, the production strategy in this time period is determined to be the most efficient production strategy. At this time, the average of various data in this time period is taken to become a standard adjustment value, and the standard adjustment value is applied to the production line, that is, the various data in the first data are adjusted to the standard adjustment value, and various production capacity indicators of the production equipment are set according to the standard adjustment value. If the expected yield rate is not achieved after application, they are adjusted one by one, and various data in this time period are replicated to the production line.

[0052] At the same time, the first data may also be recorded, and after deep learning, the production strategy may be adjusted. The deep learning process includes normalizing the sensor data, then performing data legitimacy detection on the first data, and when the data legitimacy detection result meets the legitimacy condition, performing strategy matching on the first data through a preset deep learning model, wherein the training process of the deep learning model includes:

[0053] Step S3001, before performing strategy matching on the first data through a preset deep learning model to determine a first control strategy, obtaining a historical data set;

[0054] In this embodiment, after the historical data set is obtained, the historical data set is labeled with legal data and illegal data to ensure that the model can learn to distinguish legal data from illegal data.

[0055] Step S3002, performing a data set division process on the historical data set to obtain a first data set for training and a second data set for verification, wherein the data volume ratio between the first data set and the second data set is 7:3;

[0056] In this embodiment, both the first data set and the second data set contain legal data and illegal data, and the data volume ratio of the first data set and the second data set can also be adjusted to 8:2 according to needs, and can be adjusted specifically according to needs; during the training process, the model can be adjusted through the second data set to prevent overfitting or underfitting.

[0057] Step S3003: Perform model training iterations on the preset initial deep learning model using the first data set and the second data set to obtain the trained deep learning model.

[0058] In this embodiment, during the training iteration process, model parameters such as learning rate, batch size, number of iterations, etc. can be adjusted according to the training results so that the training results meet the requirements.

[0059] Step S400: generating a first control instruction according to the first control strategy, and sending the first control instruction to the textile system to instruct the textile system to perform a target operation based on the first control instruction.

[0060] In this embodiment, a number of control instructions are generated according to the control strategy, so that the relevant equipment of the textile system acts according to the control instructions, thereby realizing the automatic control of the textile system, which greatly improves the production efficiency and control accuracy of the textile system.

[0061] Through the above steps, the deep learning model automatically generates corresponding control strategies according to different system states, so that each device in the system can be continuously rationally scheduled and controlled during the textile process, thereby effectively improving the system control accuracy and efficiency, solving the problem of low control accuracy of the textile system, and improving the control accuracy and efficiency of the textile system.

[0062] The execution subject of the above steps may be a base station, a terminal, etc., but is not limited thereto.

[0063] In an optional embodiment, the performing data legitimacy detection on the first data includes:

[0064] Step S301, performing grayscale value conversion processing on the first data to obtain a first grayscale value corresponding to the first data;

[0065] Step S302, performing pixel distribution processing on the first gray value to obtain distribution information of pixels corresponding to the first gray value;

[0066] Step S303: Perform a first legitimacy check on the distribution information through a first model to obtain a first legitimacy check result, wherein the legitimacy check result includes the first legitimacy check result.

[0067] In this embodiment, in order to more intuitively observe the legitimacy of the first data, the normalized values ​​can be converted into corresponding pixel points as grayscale values, and these pixel points are filled in a preset pixel distribution map (such as Figure 2 As shown), the legality of the relevant data is then calculated based on the distribution characteristics of these pixels (for example, whether the pixel position or the relative distance between pixels meets the requirements). If the distribution of the pixels meets the requirements, the relevant data is judged to be legal, otherwise it is judged to be illegal. This allows the correlation between different data to be intuitively observed, making it convenient for further analysis and decision-making based on the relationship between these data.

[0068] Among them, the gray value conversion can be performed by the following formula 1:

[0069] g = 255 x (Formula 1)

[0070] In the formula, x is the first data, and x is less than 1 and greater than 0. If the x value is greater than 1, the x value is directly used as the grayscale value; g is the converted grayscale value, and the range of the grayscale value g is [0,255]; the distribution information includes the position coordinates of the pixel points, the distance between the pixels, the contrast between the pixels, and other information; the first model can be an Actor-Critic model based on the deep reinforcement learning DRL model framework; in addition to judging whether the data is legal, the first legitimacy detection result can also output legitimacy scores, confidence levels, abnormal feature identifiers and other information for reference by staff.

[0071] In an optional embodiment, after performing pixel distribution processing based on the first grayscale value to obtain distribution information of pixels corresponding to the first grayscale value, the method further includes:

[0072] Step S3021, determining clustering information of the pixel points by using a preset clustering algorithm;

[0073] Step S3022: performing cluster feature comparison between the cluster information and historical cluster information, and determining that the first data is illegal when the cluster feature comparison result does not meet the preset cluster condition.

[0074] In this embodiment, in addition to judging the legitimacy of the data based on the distribution information of pixel points, the legitimacy of the data can also be judged based on the clustering relationship of pixel points. For example, the pixel points are connected in sequence, and these pixel points form an irregular polygon. The polygon is then compared with the polygon formed by historical data for overlap to determine whether the data is reasonable.

[0075] Under normal circumstances, the sensor data changes caused by the normal operation of the textile system will not change significantly, but if there are abnormal fluctuations, the sensor data will become abnormal, such as Figure 3 As shown, the pixel points are regarded as Figure 3 The scattered points AD shown are marked on the scatter plot; then these characteristic scattered points are connected according to the preset connection order to form polygonal figures, and then the areas of these polygons are calculated. The overlapping areas of these polygons can also be calculated to determine whether the changes are reasonable.

[0076] For example, Figure 3 As shown, AD is the distribution of each pixel point in time 1 (i.e., the aforementioned historical data), and A'-D' is the distribution of each pixel point in time 2 (and the aforementioned sensor data), and then the changes in the relevant data are analyzed; for example, Figure 3 The area of ​​the figure enclosed by AD is 10 under normal circumstances. When an abnormality occurs, the value of A'-D' changes, and the figure enclosed by A'-D' has an area of ​​15. The overlapping area is 8, which is larger than the figure AD. At this time, the shape and area of ​​the figure have changed significantly, thereby judging that the relevant sensor data has an abnormality.

[0077] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0078] In this embodiment, a system control device for a textile system is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made are omitted. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0079] Figure 4 is a structural block diagram of a system control device for a textile system according to an embodiment of the present invention. Figure 4 As shown, the device comprises

[0080] A data acquisition module, used for acquiring sensor data of the textile system, wherein the sensor data is obtained by sensing and detecting the textile system through a plurality of preset sensors, wherein the sensor data includes at least any one of equipment status data, working environment data and network transmission data;

[0081] A preprocessing module, used for preprocessing the sensor data to obtain first data, wherein the preprocessing includes sequentially performing data filtering and normalization processing on the sensor data;

[0082] A strategy generation module, used for obtaining result data of the finished product as second data, and determining a first control strategy according to the second data;

[0083] An instruction generation module is used to generate a first control instruction according to the first control strategy, and send the first control instruction to the textile system to instruct the textile system to perform a target operation based on the first control instruction.

[0084] In an optional embodiment, the device further comprises:

[0085] The abnormal point determination module is used to determine whether a certain item of the first data seriously deviates from the normal value when it is determined that the first data is abnormal. If all items of the first data are seriously deviated from the normal value, all items of the first data are adjusted one by one. When adjusting to a certain item of data, if the second data is higher than the preset standard yield threshold, the detection point of the data is marked as an abnormal detection point.

[0086] In an optional embodiment, the legitimacy detection module includes:

[0087] Data adjustment module: obtains the high value in the second data, and uses the first data in the high value of the second data as the standard data, takes the average of all items of data in the standard data as the standard adjustment value, and applies the standard adjustment value in the production line.

[0088] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0089] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0090] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0091] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0092] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0093] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0094] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0095] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A system control method for a textile system, characterized in that: include: Acquiring sensor data of a textile system, wherein the sensor data is obtained by performing sensor detection on the textile system through a plurality of preset sensors, wherein the sensor data includes at least any one of equipment status data, working environment data, and network transmission data; Preprocessing the sensor data to obtain first data, wherein the preprocessing includes filtering the sensor data; Acquire result data of the finished product as second data, and determine the first control strategy according to the second data; A first control instruction is generated according to the first control strategy, and the first control instruction is sent to the textile system to instruct the textile system to perform a target operation based on the first control instruction.

2. The method according to claim 1, characterized in that The step of obtaining result data of the finished product as second data and determining the first control strategy according to the second data includes: The result data of the finished product is obtained as the second data, and whether the first data is abnormal is determined according to the second data, and the first control strategy is determined according to the abnormality of the first data.

3. The method according to claim 2, characterized in that The step of obtaining result data of the finished product as the second data, determining whether the first data is abnormal according to the second data, and determining the first control strategy according to the abnormality of the first data includes: When the second data is lower than a preset standard yield rate threshold, it is determined that the first data is abnormal.

4. The method according to claim 3, characterized in that The step of obtaining result data of the finished product as the second data, determining whether the first data is abnormal according to the second data, and determining the first control strategy according to the abnormality of the first data includes: When it is determined that the first data is abnormal, determine whether a certain item of the first data seriously deviates from the normal value. If all items of the first data do not seriously deviate from the normal value, adjust all items of the first data one by one. When adjusting to a certain item of data, if the second data is higher than the preset standard yield threshold, mark the detection point of the data as an abnormal detection point.

5. The method according to claim 2, characterized in that: The step of obtaining result data of the finished product as the second data and determining the first control strategy according to the second data further includes: A high value in the second data is obtained, and the first data in the high value of the second data is used as standard data, an average of all items of data in the standard data is taken as a standard adjustment value, and the standard adjustment value is applied in the production line.

6. A system control device for a textile system, characterized in that: include: A data acquisition module, used for acquiring sensor data of the textile system, wherein the sensor data is obtained by sensing and detecting the textile system through a plurality of preset sensors, wherein the sensor data includes at least any one of equipment status data, working environment data and network transmission data; A preprocessing module, used for preprocessing the sensor data to obtain first data, wherein the preprocessing includes sequentially performing data filtering and normalization processing on the sensor data; A strategy generation module, used for obtaining result data of the finished product as second data, and determining a first control strategy according to the second data; An instruction generation module is used to generate a first control instruction according to the first control strategy, and send the first control instruction to the textile system to instruct the textile system to perform a target operation based on the first control instruction.

7. The device according to claim 6, characterized in that Also includes: An abnormal point determination module is used to determine whether a certain item of the first data seriously deviates from the normal value when it is determined that the first data is abnormal. If all items of the first data do not seriously deviate from the normal value, all items of the first data are adjusted one by one. When adjusting to a certain item of data, if the second data is higher than the preset standard yield threshold, the detection point of the data is marked as an abnormal detection point.

8. The device according to claim 6, characterized in that The legality detection module includes: Data adjustment module: obtains the high value in the second data, and uses the first data in the high value of the second data as the standard data, takes the average of all items of data in the standard data as the standard adjustment value, and applies the standard adjustment value in the production line.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 5 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 5.

Images